中文
相关论文

相关论文: Off-policy Maximum Entropy Reinforcement Learning …

200 篇论文

Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the…

机器学习 · 计算机科学 2021-09-27 Chayan Banerjee , Zhiyong Chen , Nasimul Noman

Soft actor-critic (SAC) is a popular algorithm for max-entropy reinforcement learning. In practice, the energy-based policies in SAC are often approximated using simple policy classes for efficiency, sacrificing the expressiveness and…

机器学习 · 计算机科学 2026-01-01 Yuyang Zhang , Yang Hu , Bo Dai , Na Li

Mixture models are an expressive hypothesis class that can approximate a rich set of policies. However, using mixture policies in the Maximum Entropy (MaxEnt) framework is not straightforward. The entropy of a mixture model is not equal to…

机器学习 · 计算机科学 2021-03-19 Nir Baram , Guy Tennenholtz , Shie Mannor

Actor-critic (AC) algorithms are known for their efficacy and high performance in solving reinforcement learning problems, but they also suffer from low sampling efficiency. An AC based policy optimization process is iterative and needs to…

机器学习 · 计算机科学 2021-12-02 Chayan Banerjee , Zhiyong Chen , Nasimul Noman , Mohsen Zamani

Soft Actor-Critic (SAC) is one of the state-of-the-art off-policy reinforcement learning (RL) algorithms that is within the maximum entropy based RL framework. SAC is demonstrated to perform very well in a list of continous control tasks…

机器学习 · 计算机科学 2021-12-22 Zhenyang Shi , Surya P. N. Singh

Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample…

Model-free deep reinforcement learning (RL) algorithms have been demonstrated on a range of challenging decision making and control tasks. However, these methods typically suffer from two major challenges: very high sample complexity and…

机器学习 · 计算机科学 2018-08-10 Tuomas Haarnoja , Aurick Zhou , Pieter Abbeel , Sergey Levine

Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly…

机器学习 · 计算机科学 2018-10-25 Esther Derman , Daniel J. Mankowitz , Timothy A. Mann , Shie Mannor

In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update…

机器学习 · 计算机科学 2019-03-25 Yan Zhang , Michael M. Zavlanos

We propose a new policy iteration theory as an important extension of soft policy iteration and Soft Actor-Critic (SAC), one of the most efficient model free algorithms for deep reinforcement learning. Supported by the new theory, arbitrary…

机器学习 · 计算机科学 2019-02-18 Gang Chen , Yiming Peng

In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss…

机器学习 · 计算机科学 2019-10-09 Xue Bin Peng , Aviral Kumar , Grace Zhang , Sergey Levine

Off-policy evaluation is a key component of reinforcement learning which evaluates a target policy with offline data collected from behavior policies. It is a crucial step towards safe reinforcement learning and has been used in…

机器学习 · 计算机科学 2020-12-01 Jinlin Lai , Lixin Zou , Jiaxing Song

Designing off-policy reinforcement learning algorithms is typically a very challenging task, because a desirable iteration update often involves an expectation over an on-policy distribution. Prior off-policy actor-critic (AC) algorithms…

机器学习 · 计算机科学 2021-07-20 Tengyu Xu , Zhuoran Yang , Zhaoran Wang , Yingbin Liang

This paper proposes an off-policy risk-sensitive reinforcement learning based control framework for stabilization of a continuous-time nonlinear system that subjects to additive disturbances, input saturation, and state constraints. By…

系统与控制 · 电气工程与系统科学 2022-04-21 Cong Li , Qingchen Liu , Zhehua Zhou , Martin Buss , Fangzhou Liu

In this work, we consider policy-based methods for solving the reinforcement learning problem, and establish the sample complexity guarantees. A policy-based algorithm typically consists of an actor and a critic. We consider using various…

机器学习 · 计算机科学 2023-01-16 Zaiwei Chen , Siva Theja Maguluri

The beneficial effects of treatments vary across individuals in most studies. Treatment heterogeneity motivates practitioners to search for the optimal policy based on personal characteristics. A long-standing common practice in policy…

统计理论 · 数学 2025-01-06 Xuqiao Li , Ying Yan

Learning expressive stochastic policies instead of deterministic ones has been proposed to achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy Reinforcement Learning (MaxEnt RL), the policy is modeled as…

机器学习 · 计算机科学 2024-05-03 Safa Messaoud , Billel Mokeddem , Zhenghai Xue , Linsey Pang , Bo An , Haipeng Chen , Sanjay Chawla

Safe offline reinforcement learning aims to learn policies that maximize cumulative rewards while adhering to safety constraints, using only offline data for training. A key challenge is balancing safety and performance, particularly when…

机器学习 · 计算机科学 2024-12-13 Prajwal Koirala , Zhanhong Jiang , Soumik Sarkar , Cody Fleming

The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the meta reinforcement learning literature much recent work has…

We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each…

多智能体系统 · 计算机科学 2021-11-02 Kuo Li , Qing-Shan Jia
‹ 上一页 1 2 3 10 下一页 ›